The collection of telephone databases, for training speech recognisers, is a time consuming and costly work. In the paper we propose a method for producing simulated telephone data starting from clean wide band databases. The result of the simulation is the generation of a noisy database that can be used, in addition to other techniques, for compensating or adapting speech recogniser parameters with respect to different test environments. For the first of the two adopted test sets, performance improvements ranging from about 30% to about 9% have been measured, as a function of the quantity of real telephone data used, in addition to the simulated ones, for system training. For the second test set no significant improvements were obtained.
Cite as: Tarcisio, C., Daniele, F., Roberto, G., Marco, O. (1999) Use of simulated data for robust telephone speech recognition. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2825-2828, doi: 10.21437/Eurospeech.1999-624
@inproceedings{tarcisio99_eurospeech,
author={Coianiz Tarcisio and Falavigna Daniele and Gretter Roberto and Orlandi Marco},
title={{Use of simulated data for robust telephone speech recognition}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2825--2828},
doi={10.21437/Eurospeech.1999-624}
}